Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for China. Source: Global Dialogues GD1 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.7 Sonnet | Claude 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 92.3% | 6th 91.0% | 1st 93.0% | 11th 88.8% | 16th 85.8% | 20th 82.3% | 7th 89.8% | 13th 87.0% | 19th 84.3% | 17th 85.0% | 10th 89.3% | 5th 91.5% | 3rd 92.5% | 21st 77.3% | 2nd 92.5% | 14th 86.8% | 15th 86.5% | 17th 85.0% | 12th 88.0% | 8th 89.5% | 8th 89.5% | |
| 87.9% | 96% | 96% | 98% | 87% | 85% | 70% | 85% | 83% | 88% | 81% | 87% | 89% | 97% | 71% | 90% | 95% | 92% | 80% | 91% | 88% | 96% | |
| 88.3% | 94% | 88% | 94% | 91% | 85% | 86% | 88% | 88% | 84% | 83% | 92% | 93% | 89% | 87% | 97% | 83% | 82% | 86% | 89% | 89% | 87% | |
| 85.1% | 89% | 89% | 89% | 89% | 89% | 88% | 92% | 86% | 78% | 83% | 86% | 88% | 88% | 65% | 87% | 82% | 83% | 83% | 80% | 90% | 84% | |
| 90.5% | 90% | 91% | 91% | 88% | 84% | 85% | 94% | 91% | 87% | 93% | 92% | 96% | 96% | 86% | 96% | 87% | 89% | 91% | 92% | 91% | 91% |